Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes

By Abhinav Shrivastava, Saurabh Singh, Abhinav Kumar Gupta. 2012

101 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Webly Supervised Learning of Convolutional Networks (2015, methodology): “Inspired by this, we want to train CNNs with such relationships - with their simplest form being pair-wise look-alike relationships [46, 9, 12].”
The More You Know: Using Knowledge Graphs for Image Classification (2016, background): “Our work is also related to attribute approaches [8] to vision such as [16] which uses a fixed set of binary attributes to do zero-shot prediction, [34] which uses attributes shared across categories to prevent semantic drift in semi-supervised learning and [5] which automatically discovers attribut”
Watch and learn: Semi-supervised learning of object detectors from videos (2015, methodology): “One major body of work [7, 8, 12, 31, 46] tries to overcome this difficulty by leveraging the use of a set of pre-defined attributes for image classes [8, 46] and additionally web-supervision and text [7, 12].”
Fine-Grained Visual Comparisons with Local Learning (2014, unknown): “, “a mule has a tail longer than a donkey’s” [5, 28, 30].”
KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA (2020, background): “Some of the earliest versions of this work was relating to attributes [19, 67] or knowledge mined from the web [63], often for zero- or few-shot learning problems [20, 37, 62], as well as for finegrained classification [18].”
Unsupervised Joint Mining of Deep Features and Image Labels for Large-Scale Radiology Image Categorization and Scene Recognition (2017, background): “, image patches [53, 13, 34, 60], parts/segments [27, 54, 2], prototypes [11], attributes [51, 7] through different learning and mining techniques, e.”
Learning Compositional Representations for Few-Shot Recognition (2018, background): “In [34] attributes are used to explicitly provide constraints when learning from a small number of labeled and a large number of unlabeled images.”
Learning Attributes Equals Multi-Source Domain Generalization (2016, background): “Attributes also reveal the rich structures underlying categories and are thus often employed to regulate machine learning models for visual recognition [69, 73, 45, 63, 33, 22, 21, 62].”
NEIL: Extracting Visual Knowledge from Web Data (2013, methodology): “An alternative approach is to use visual recognition for extracting these datasets automatically from the Internet [23] [34] [36].”
Transfer Learning in a Transductive Setting (2013, methodology): “More specifically [27] propose to bootstrap classifiers by adding unlabeled data.”
Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images (2016, background): “Attribute Comparisons Since the introduction of relative attributes [28], the task of attribute comparisons has gained attention for its variety of applications, such as online shopping [19], biometrics [32], novel forms of lowsupervision learning [2, 36], and font selection [26].”
Label Propagation for Deep Semi-Supervised Learning (2019, background): “The same holds for SSL in image classification [10, 16, 4, 37].”
Automatic Image Dataset Construction from Click-through Logs Using Deep Neural Network (2015, background): “These labelled images can be manually labelled [21] or top-ranked images from image search engines [2, 7, 17].”